@inproceedings{jin-etal-2019-low,
    title = "Low-Rank {HOCA}: Efficient High-Order Cross-Modal Attention for Video Captioning",
    author = "Jin, Tao  and
      Huang, Siyu  and
      Li, Yingming  and
      Zhang, Zhongfei",
    editor = "Inui, Kentaro  and
      Jiang, Jing  and
      Ng, Vincent  and
      Wan, Xiaojun",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
    month = nov,
    year = "2019",
    address = "Hong Kong, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/D19-1207/",
    doi = "10.18653/v1/D19-1207",
    pages = "2001--2011"
}